Part-of-speech tagging with recurrent neural networks

Pérez-Ortiz, Juan Antonio; Forcada, Mikel L.

doi:10.1109/ijcnn.2001.938396

Cited by 17 publications

(5 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…PoS tag may be very coarse (e.g: Ve "Verb") or very fine (e.g: VePiMaPlFsSj "Verb, Imperfect, Masculine, Plural, First Person, Subjunctive"), depending on the task or application [11]. Since the main aim of AMT system is to produce a tagged corpus, tags were developed with a good level of granularity, inflectional features were added to each tag, that satisfied what linguists and NLP developers need.…”

Section: Experimental Results and Analysismentioning

confidence: 99%

Towards Developing a Comprehensive Tag Set for the Arabic Language

Alqrainy

Alawairdhi

2020

Journal of Intelligent Systems

View full text Add to dashboard Cite

This paper presents a comprehensive Tag set as a fundamental component for developing an automated Word Class/Part-of-Speech (PoS) tagging system for the Arabic language. The aim is to develop a standard and comprehensive PoS tag set that based upon PoS classes and Arabic inflectional morphology useful for Linguistics and Natural Language Processing (NLP) developers to extract more linguistic information from it. The tag names in the developed tag set uses terminology from Arabic tradition grammar rather than English grammar. The usability of the presented Tag set has been tested in manual tagging and built up a set of tagged text to serve as a goal corpus used to compare it with the results obtained from the tagger. The tagger has achieved an average accuracy of 90% using the developed detailed tag set.

show abstract

Section: Experimental Results and Analysismentioning

confidence: 99%

Towards Developing a Comprehensive Tag Set for the Arabic Language

Alqrainy

Alawairdhi

2020

Journal of Intelligent Systems

View full text Add to dashboard Cite

show abstract

“…Pun, Eng or other. The use of the deep neural network for sequence labelling tasks like Part of Speech (POS) tagging and Named Entity Recognition (NER) has been explored by various researchers in recent years (Chen et al , 2010; Chiu and Nichols 2016a, 2016b; Dos Santos and Guimarães, 2015; Dos Santos and Zadrozny, 2014; Perez-Ortiz and Forcada, 2001; Sutskever et al , 2014; Tamburini, 2016). Zazo et al (2016) also employed the techniques in the speech recognition domain.…”

Section: Methodsmentioning

confidence: 99%

Roman to Gurmukhi Social Media Text Normalization

Kaur

Singh

2020

IJICC

View full text Add to dashboard Cite

PurposeNormalization is an important step in all the natural language processing applications that are handling social media text. The text from social media poses a different kind of problems that are not present in regular text. Recently, a considerable amount of work has been done in this direction, but mostly in the English language. People who do not speak English code mixed the text with their native language and posted text on social media using the Roman script. This kind of text further aggravates the problem of normalizing. This paper aims to discuss the concept of normalization with respect to code-mixed social media text, and a model has been proposed to normalize such text.Design/methodology/approachThe system is divided into two phases – candidate generation and most probable sentence selection. Candidate generation task is treated as machine translation task where the Roman text is treated as source language and Gurmukhi text is treated as the target language. Character-based translation system has been proposed to generate candidate tokens. Once candidates are generated, the second phase uses the beam search method for selecting the most probable sentence based on hidden Markov model.FindingsCharacter error rate (CER) and bilingual evaluation understudy (BLEU) score are reported. The proposed system has been compared with Akhar software and RB\_R2G system, which are also capable of transliterating Roman text to Gurmukhi. The performance of the system outperforms Akhar software. The CER and BLEU scores are 0.268121 and 0.6807939, respectively, for ill-formed text.Research limitations/implicationsIt was observed that the system produces dialectical variations of a word or the word with minor errors like diacritic missing. Spell checker can improve the output of the system by correcting these minor errors. Extensive experimentation is needed for optimizing language identifier, which will further help in improving the output. The language model also seeks further exploration. Inclusion of wider context, particularly from social media text, is an important area that deserves further investigation.Practical implicationsThe practical implications of this study are: (1) development of parallel dataset containing Roman and Gurmukhi text; (2) development of dataset annotated with language tag; (3) development of the normalizing system, which is first of its kind and proposes translation based solution for normalizing noisy social media text from Roman to Gurmukhi. It can be extended for any pair of scripts. (4) The proposed system can be used for better analysis of social media text. Theoretically, our study helps in better understanding of text normalization in social media context and opens the doors for further research in multilingual social media text normalization.Originality/valueExisting research work focus on normalizing monolingual text. This study contributes towards the development of a normalization system for multilingual text.

show abstract

“…Collobert et al [25] built a CNN neural network for multiple sequence labeling tasks, which gives state-of-the-art POS results. Recurrent neural network models have also been used for this task [49,50]. Huang et al [50] combines bidirectional LSTM with a CRF layer, their model is robust and has less dependence on word embedding.…”

Section: Related Workmentioning

confidence: 99%

Combining Discrete and Neural Features for Sequence Labeling

Yang

Teng

Zhang

et al. 2018

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Neural network models have recently 1 received heated research attention in the natural language processing community. Compared with traditional models with discrete features, neural models have two main advantages. First, they take low-dimensional, real-valued embedding vectors as inputs, which can be trained over large raw data, thereby addressing the issue of feature sparsity in discrete models. Second, deep neural networks can be used to automatically combine input features, and including non-local features that capture semantic patterns that cannot be expressed using discrete indicator features. As a result, neural network models have achieved competitive accuracies compared with the best discrete models for a range of NLP tasks. On the other hand, manual feature templates have been carefully investigated for most NLP tasks over decades and typically cover the most useful indicator pattern for solving the problems. Such information can be complementary the features automatically induced from neural networks, and therefore combining discrete and neural features can potentially lead to better accuracy compared with models that leverage discrete or neural features only. In this paper, we systematically investigate the effect of discrete and neural feature combination for a range of fundamental NLP tasks based on sequence labeling, including word segmentation, POS tagging and named entity recognition for Chinese and English, respectively. Our results on standard benchmarks show that state-of-the-art neural models can give accuracies comparable to the best discrete models in the literature for most tasks and combing discrete and neural features unanimously yield better results.

show abstract

Part-of-speech tagging with recurrent neural networks

Abstract: Abstract

Cited by 17 publications

References 13 publications

Towards Developing a Comprehensive Tag Set for the Arabic Language

Towards Developing a Comprehensive Tag Set for the Arabic Language

Roman to Gurmukhi Social Media Text Normalization

Combining Discrete and Neural Features for Sequence Labeling

Contact Info

Product

Resources

About